Hacker News: tnspacetime

New comment by tnspacetime in "Show HN: Flipflop – Iroh-powered persistent tunnels for filesharing"

tnspacetime — Thu, 15 Oct 2026 17:01:13 +0000

Ok nice find! Did you try it?

Pig: Pi in Go, a port that plans on keeping up

tnspacetime — Sun, 27 Sep 2026 12:59:22 +0000

Article URL: https://developer.hpe.com/blog/meet-pig-pi-in-go-a-port-that-plans-on-keeping-up/

Comments URL: https://news.ycombinator.com/item?id=49866296

Points: 6

# Comments: 5

New comment by tnspacetime in "Show HN: Reladraw – A diagram language where you decide where to place things"

tnspacetime — Sat, 26 Sep 2026 23:37:37 +0000

This seems nice but I’ll need to read the syntax more carefully to see how capable and convenient it is.

New comment by tnspacetime in "Show HN: Whiteboard (YC W26) – An open-source IDE for thoughtful software design"

tnspacetime — Thu, 24 Sep 2026 22:12:13 +0000

The point about semantic diff viewer sounds very interesting. I think many coding harnesses are not doing this well enough.

New comment by tnspacetime in "What Is RLCD? The Secret Behind Jev"

tnspacetime — Thu, 24 Sep 2026 17:31:42 +0000

If you need any background info on Jev read this:

https://software.human-tokens.dev/

New comment by tnspacetime in "What Is RLCD? The Secret Behind Jev"

tnspacetime — Thu, 24 Sep 2026 17:26:57 +0000

I have not studied it properly too. Good that it has both code and note though.

What Is RLCD? The Secret Behind Jev

tnspacetime — Thu, 24 Sep 2026 12:21:16 +0000

Article URL: https://di-zhang-llm.github.io/blog/what-is-rlcd-the-secret-behind-jev/

Comments URL: https://news.ycombinator.com/item?id=49829625

Points: 68

# Comments: 8

New comment by tnspacetime in "Show HN: Mini-AGI – Dynamic continual learning model trained on 8GB VRAM"

tnspacetime — Tue, 22 Sep 2026 21:05:12 +0000

I think as an experiment your setup is interesting. But in realistic systems even standard evals, i.e. making sure things work well for normal use cases, are already enormous, let alone thinking about catastrophic forgetting.

New comment by tnspacetime in "Show HN: Mini-AGI – Dynamic continual learning model trained on 8GB VRAM"

tnspacetime — Tue, 22 Sep 2026 15:44:27 +0000

Yes I read that one, and that’s why I said the explanation is not clear. Anyway, catastrophic forgetting is theoretically not possible. “ Existing capability must substantially learn new information, so its representation must change, while retaining its still-valid old knowledge”. I think your setup is demonstrating something weaker.

New comment by tnspacetime in "Show HN: Lossless-memory – a personal AI memory that never summarizes"

tnspacetime — Tue, 22 Sep 2026 14:03:55 +0000

This is sort of clever! It seems to me though you can almost design a small dsl and you don’t need ai at all.

New comment by tnspacetime in "Show HN: Mini-AGI – Dynamic continual learning model trained on 8GB VRAM"

tnspacetime — Tue, 22 Sep 2026 12:40:03 +0000

I read your github page and there's mention of continual learning but no argument how catastrophic forgetting is avoided. I think you should explain that better.